INDEX
Explanations
references to Russia and its related entities or activities
New Auto-Interp
Negative Logits
GeneratedValue
-0.96
extAlignment
-0.94
FormControl
-0.94
Hend
-0.86
Personendaten
-0.86
AccessorTable
-0.84
AntiForgeryToken
-0.83
apimachinery
-0.81
ophen
-0.79
oinette
-0.79
POSITIVE LOGITS
Russia
1.40
Russians
1.20
Rusia
1.20
Russia
1.19
Russian
1.18
RUSS
1.13
Russie
1.10
Russo
1.05
Russian
0.99
RUSS
0.95
Activations Density 0.108%